The heat of the afternoon had settled into a heavy stupor, and she felt the effects most keenly as she ascended the steep staircase. Her head throbbed faintly. Reaching the attic felt like conquering Everest. She’d really rather be anywhere else.

The air was dense, thick with the scent of forgotten things. Dust motes danced in the lone ray of sunlight. She felt the muscles in her neck tighten as she surveyed the space. A deep sigh escaped her.

She stumbled upon a collection of old journals tucked away in a trunk. Picking one up, she ran her thumb across the cover. It was a well-worn leather-bound book, and the promise of stories within sparked a fleeting interest. A new purpose, even if it was just for a moment.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214